Auditing Learned Associations in Deep Learning Approaches to Extract Race and Ethnicity from Clinical Text.
AMIA Annu Symp Proc
; 2023: 289-298, 2023.
Article
en En
| MEDLINE
| ID: mdl-38222422
ABSTRACT
Complete and accurate race and ethnicity (RE) patient information is important for many areas of biomedical informatics research, such as defining and characterizing cohorts, performing quality assessments, and identifying health inequities. Patient-level RE data is often inaccurate or missing in structured sources, but can be supplemented through clinical notes and natural language processing (NLP). While NLP has made many improvements in recent years with large language models, bias remains an often-unaddressed concern, with research showing that harmful and negative language is more often used for certain racial/ethnic groups than others. We present an approach to audit the learned associations of models trained to identify RE information in clinical text by measuring the concordance between model-derived salient features and manually identified RE-related spans of text. We show that while models perform well on the surface, there exist concerning learned associations and potential for future harms from RE-identification models if left unaddressed.
Texto completo:
1
Colección:
01-internacional
Banco de datos:
MEDLINE
Asunto principal:
Etnicidad
/
Aprendizaje Profundo
Tipo de estudio:
Risk_factors_studies
Límite:
Humans
Idioma:
En
Revista:
AMIA Annu Symp Proc
Asunto de la revista:
INFORMATICA MEDICA
Año:
2023
Tipo del documento:
Article